ACE-Step open music foundation model via Replicate. Generates up to 4 minutes of music with vocals from style tags and structured lyrics, with full control over steps, scheduler and guidance. Billed per second of requested duration.
Test this model instantly in the Console Playground โ no code required
Copy usage instructions for Claude, ChatGPT, or other AI
curl -X POST "https://api.core.today/v1/predictions" \
-H "Content-Type: application/json" \
-H "X-API-Key: cdt_your_api_key" \
-d '{
"model": "lucataco/ace-step",
"input": {
"tags": "k-pop, electro-pop, company jingle, synth brass, punchy drums, 128 BPM, energetic, playful, female vocals, korean",
"lyrics": "[verse]\n์์นจ๋ถํฐ AI, ์ปคํผ๋ณด๋ค ์งํด\n์ฝ๋ฉํ๋ค ๋ณด๋ ๋ฒ์จ ์๋ฒฝ ๋ ์๋ค!\n์ ๋๋ ๊ฑด ์์ด, ์ผ๋จ ๋ง๋ค์ด ๋ด\n์์์ด ํ์ค ๋๋ ๋ง๋ฒ ๊ฐ์ ํ์ฌ!\n\n[chorus]\n์ฝ์ด! ๋ท! ํฌ๋ฐ์ด!\n์ค๋์ ์์์ด ๋ด์ผ์ ๊ธฐ์ ๋ก!\n์ฝ์ด! ๋ท! ํฌ๋ฐ์ด!\nAI๋ ๋๋ผ๋ ์ฐ๋ฆฌ์ ์์ด๋์ด!\n\n[outro]\n๋๋ฑ๋๋ฑ ๋ง๋ค๊ณ , ๋ฐ์ง๋ฐ์ง ๋น๋ด๊ณ !\n๊ธฐ์ ์ ๋์ด ๊ฒฝํ์ผ๋ก!\n์ฝ์ด๋ทํฌ๋ฐ์ด, Hey!",
"duration": 60
}
}'| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
tags | string | Yes | - | Comma-separated style tags, e.g. 'synth-pop, electronic, 128 BPM, energetic' |
lyrics | string | No | - | Lyrics with [verse], [chorus], [bridge] sections. Use [instrumental] or [inst] for instrumental music |
duration | number | No | 60 | Duration of the generated audio in seconds (1-240). Billed per second |
number_of_steps | integer | No | 60 | Number of inference steps (10-200) |
seed | integer | No | -1 | Random seed. -1 randomizes |
scheduler | string | No | euler | Scheduler type eulerheun |
guidance_type | string | No | apg | Guidance type for CFG apgcfgcfg_star |
guidance_scale | number | No | 15 | Overall guidance scale (0-30) |
granularity_scale | number | No | 10 | Omega scale for APG guidance (-100 to 100) |
guidance_interval | number | No | 0.5 | Guidance interval (0-1) |
guidance_interval_decay | number | No | 0 | Guidance interval decay (0-1) |
min_guidance_scale | number | No | 3 | Minimum guidance scale (0-100) |
tag_guidance_scale | number | No | 0 | Guidance scale for tags (0-10) |
lyric_guidance_scale | number | No | 0 | Guidance scale for lyrics (0-10) |
Common parameters used when calling POST /v1/predictions.
| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
model | string | Yes | - | Model identifier |
input | object | Yes | - | Object containing the model-specific parameters from the table above |
output_folder | string | No | - | Folder path for output files (max 256 chars, '..' not allowed) |
webhook_url | string | No | - | Webhook URL to call on completion |
is_public | boolean | No | false | If true, output files are also available via permanent public URLs |
The same Korean company-song lyrics given to every music model โ compare how each one sings them
curl -X POST "https://api.core.today/v1/predictions" \
-H "Content-Type: application/json" \
-H "X-API-Key: cdt_your_api_key" \
-d '{
"model": "lucataco/ace-step",
"input": {
"tags": "k-pop, electro-pop, company jingle, synth brass, punchy drums, 128 BPM, energetic, playful, female vocals, korean",
"lyrics": "[verse]\n์์นจ๋ถํฐ AI, ์ปคํผ๋ณด๋ค ์งํด\n์ฝ๋ฉํ๋ค ๋ณด๋ ๋ฒ์จ ์๋ฒฝ ๋ ์๋ค!\n์ ๋๋ ๊ฑด ์์ด, ์ผ๋จ ๋ง๋ค์ด ๋ด\n์์์ด ํ์ค ๋๋ ๋ง๋ฒ ๊ฐ์ ํ์ฌ!\n\n[chorus]\n์ฝ์ด! ๋ท! ํฌ๋ฐ์ด!\n์ค๋์ ์์์ด ๋ด์ผ์ ๊ธฐ์ ๋ก!\n์ฝ์ด! ๋ท! ํฌ๋ฐ์ด!\nAI๋ ๋๋ผ๋ ์ฐ๋ฆฌ์ ์์ด๋์ด!\n\n[outro]\n๋๋ฑ๋๋ฑ ๋ง๋ค๊ณ , ๋ฐ์ง๋ฐ์ง ๋น๋ด๊ณ !\n๊ธฐ์ ์ ๋์ด ๊ฒฝํ์ผ๋ก!\n์ฝ์ด๋ทํฌ๋ฐ์ด, Hey!",
"duration": 60
}
}'Tag prompt plus sectioned lyrics, 60 seconds
curl -X POST "https://api.core.today/v1/predictions" \
-H "Content-Type: application/json" \
-H "X-API-Key: cdt_your_api_key" \
-d '{
"model": "lucataco/ace-step",
"input": {
"tags": "synth-pop, electronic, pop, synthesizer, drums, bass, piano, 128 BPM, energetic, uplifting, modern",
"lyrics": "[verse]\nWoke up in a city that's always alive\nNeon lights they shimmer they thrive\n\n[chorus]\nOh we ride the night\nelectric hearts alight",
"duration": 60
}
}'POST /v1/predictions